Large self-supervised pre-trained speech models require computationally
...
In this paper, we propose ACA-Net, a lightweight, global context-aware
s...
Monaural speech enhancement has been widely studied using real networks ...
Transformer based models have provided significant performance improveme...
Convolutional recurrent networks (CRN) integrating a convolutional
encod...
Echo and noise suppression is an integral part of a full-duplex communic...
Deep complex U-Net structure and convolutional recurrent network (CRN)
s...
Cross-lingual voice conversion (VC) is an important and challenging prob...
Recent state-of-the-art neural text-to-speech (TTS) synthesis models hav...